Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of users or user-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to user-related concepts and interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.64
     Beir
    -0.64
     Roof
    -0.64
    amer
    -0.63
     Winning
    -0.62
     Tempest
    -0.61
     Baptist
    -0.60
    LECT
    -0.60
    forth
    -0.60
     offic
    -0.59
    POSITIVE LOGITS
     interface
    1.20
    interface
    1.11
     interfaces
    1.08
     Interface
    1.08
    agent
    0.98
    pace
    0.98
    Agent
    0.97
    cript
    0.94
    base
    0.94
    Interface
    0.86
    Act Density 0.039%

    No Known Activations